Máster en Data Science UAH

Tasador de viviendas de alquiler vacacional en Valencia

Notebook #3 - Estudio de la localización

Alumno: Héctor Mateos Oblanca
Tutor: Daniel Rodríguez Pérez

Intro

In [1]:
city = 'valencia'
month = '201909'
filename_in = 'src/data/' + city + '-' + month + '-listings-CLEAN.csv'
In [2]:
import math
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from IPython.display import display, HTML
import featuretools as ft
import uuid
import s2sphere as s2
import random
 
from kmodes.kmodes import KModes
from sklearn.ensemble import RandomForestRegressor
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
from sklearn.model_selection import train_test_split, GridSearchCV, cross_val_score, cross_val_predict 
from sklearn.metrics import r2_score, mean_squared_error, mean_absolute_error

import scipy.spatial as spatial
import plotly.express as px
import chart_studio.plotly as py
import plotly.graph_objs as go
from plotly.offline import iplot, init_notebook_mode

%run src/utils.py
In [3]:
coefs = {}
metrics = {}

def collect_results(columns, model, method, r2, mae, mse, skip_coef=True):
    # coefs
    if skip_coef != True:
        method_coefs = {}
        if hasattr(model, '__intercept'):
            method_coefs['__intercept'] = model.intercept_
        
        for i in range(len(columns.values)):
            method_coefs[columns.values[i]] = abs(model.coef_[i])
        coefs[method] = method_coefs
        df_coefs = pd.DataFrame(coefs)
        df_coefs = df_coefs.sort_values(by=method, ascending=False)
        display(df_coefs)
    
    # metrics
    metrics[method] = {
        'R2':r2.round(3),
        'MAE':mae.round(3),
        'MSE':mse.round(3)
    }
    
    display(pd.DataFrame(metrics))

def print_feature_importances(method, importances, df):
    feature_score = pd.DataFrame(list(zip(df.dtypes.index, importances)), columns=['Feature','Score'])
    feature_score = feature_score.sort_values(by='Score', 
                                              ascending=True, 
                                              inplace=False, 
                                              kind='quicksort', 
                                              na_position='last')
    
    fig = go.Figure(
        go.Bar(
            x=feature_score['Score'],
            y=feature_score['Feature'],
            orientation='h'
        )
    )
    
    fig.update_layout(
        title=method + " Feature Importance Ranking",
        height=25*len(feature_score)
    )
    
    fig.show()

Carga del dataset

In [4]:
df = pd.read_csv(filename_in)
df.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 5471 entries, 0 to 5470
Data columns (total 72 columns):
host_response_time                        5471 non-null object
latitude                                  5471 non-null float64
longitude                                 5471 non-null float64
property_type                             5471 non-null object
room_type                                 5471 non-null object
accommodates                              5471 non-null int64
bathrooms                                 5471 non-null float64
bedrooms                                  5471 non-null float64
price                                     5471 non-null float64
security_deposit                          5471 non-null float64
cleaning_fee                              5471 non-null float64
guests_included                           5471 non-null int64
extra_people                              5471 non-null float64
minimum_nights_avg_ntm                    5471 non-null float64
maximum_nights_avg_ntm                    5471 non-null float64
number_of_reviews                         5471 non-null int64
number_of_reviews_ltm                     5471 non-null int64
first_review                              5471 non-null object
last_review                               5471 non-null object
review_scores_rating                      5464 non-null float64
review_scores_accuracy                    5464 non-null float64
review_scores_cleanliness                 5464 non-null float64
review_scores_checkin                     5464 non-null float64
review_scores_communication               5464 non-null float64
review_scores_location                    5464 non-null float64
review_scores_value                       5464 non-null float64
instant_bookable                          5471 non-null int64
cancellation_policy                       5471 non-null object
reviews_per_month                         5471 non-null float64
district                                  5471 non-null object
neighbourhood                             5471 non-null object
has_wifi                                  5471 non-null int64
has_essentials                            5471 non-null int64
has_kitchen                               5471 non-null int64
has_heating                               5471 non-null int64
has_washer                                5471 non-null int64
has_hangers                               5471 non-null int64
has_tv                                    5471 non-null int64
has_hair_dryer                            5471 non-null int64
has_iron                                  5471 non-null int64
has_shampoo                               5471 non-null int64
has_laptop_friendly_workspace             5471 non-null int64
has_air_conditioning                      5471 non-null int64
has_hot_water                             5471 non-null int64
has_elevator                              5471 non-null int64
has_refrigerator                          5471 non-null int64
has_dishes_and_silverware                 5471 non-null int64
has_microwave                             5471 non-null int64
has_bed_linens                            5471 non-null int64
has_no_stairs_or_steps_to_enter           5471 non-null int64
has_coffee_maker                          5471 non-null int64
has_cooking_basics                        5471 non-null int64
has_family/kid_friendly                   5471 non-null int64
has_long_term_stays_allowed               5471 non-null int64
has_first_aid_kit                         5471 non-null int64
has_oven                                  5471 non-null int64
has_stove                                 5471 non-null int64
host_verified_by_phone                    5471 non-null int64
host_verified_by_email                    5471 non-null int64
host_verified_by_government_id            5471 non-null int64
host_verified_by_reviews                  5471 non-null int64
host_verified_by_jumio                    5471 non-null int64
host_verified_by_offline_government_id    5471 non-null int64
host_verified_by_selfie                   5471 non-null int64
host_verified_by_identity_manual          5471 non-null int64
host_verified_by_facebook                 5471 non-null int64
host_verified_by_work_email               5471 non-null int64
host_verified_by_google                   5471 non-null int64
has_license                               5471 non-null int64
activity_months                           5471 non-null float64
income_med_occupation                     5471 non-null float64
price_med_occupation_per_accommodate      5471 non-null float64
dtypes: float64(21), int64(43), object(8)
memory usage: 3.0+ MB

Descarte de características

In [5]:
useful_cols = [
    'accommodates',
    'bathrooms',
    'bedrooms',
    'cancellation_policy',
    'cleaning_fee',
    'extra_people',
    'guests_included',
    'has_air_conditioning',
    'has_bed_linens',
    'has_coffee_maker',
    'has_cooking_basics',
    'has_dishes_and_silverware',
    'has_elevator',
    'has_essentials',
    'has_family/kid_friendly',
    'has_first_aid_kit',
    'has_hair_dryer',
    'has_hangers',
    'has_heating',
    'has_hot_water',
    'has_iron',
    'has_kitchen',
    'has_laptop_friendly_workspace',
    'has_license',
    'has_long_term_stays_allowed',
    'has_microwave',
    'has_no_stairs_or_steps_to_enter',
    'has_oven',
    'has_refrigerator',
    'has_shampoo',
    'has_stove',
    'has_tv',
    'has_washer',
    'has_wifi',
    'instant_bookable',
    'latitude',
    'longitude',
    'maximum_nights_avg_ntm',
    'minimum_nights_avg_ntm',
    'neighbourhood',
    'price',
    'property_type',
    'room_type',
    'security_deposit'
]

useless_cols = [
    'district',
    'income_med_occupation',
    'activity_months',
    'first_review',
    'last_review',
    'number_of_reviews',
    'number_of_reviews_ltm',
    'review_scores_rating',
    'review_scores_accuracy',
    'review_scores_cleanliness',
    'review_scores_checkin',
    'review_scores_communication',
    'review_scores_location',
    'review_scores_value',
    'reviews_per_month'
]

highly_corr_cols = [
    'has_refrigerator', 
    'host_verified_by_selfie'
]

df.drop([*useless_cols, *highly_corr_cols], axis=1, errors='ignore', inplace=True)
df.shape
Out[5]:
(5471, 55)

Nuevas características de localización calculadas

Distancia a puntos de interés

Se calcula para cada propiedad la distancia en kilómetros a diferentes puntos de interés turístico de la ciudad.

In [6]:
pois = [    
    {'name':'ciudad-artes-ciencias', 'coord':(39.459896, -0.35399)},
    {'name':'estadio-mestalla', 'coord':(39.474722, -0.358333)},
    {'name':'torres-serranos', 'coord':(39.4792, -0.3760)},
    {'name':'lonja-seda', 'coord':(39.474417, -0.378444)},
    {'name':'catedral', 'coord':(39.4756, -0.3752)},
    {'name':'ayuntamiento', 'coord':(39.46667, -0.375)},
    {'name':'estacion-joaquin-sorolla', 'coord':(39.466953, -0.377129)},
    {'name':'aeropuerto', 'coord':(39.489444444444, -0.48166666666667)}
]
In [7]:
for poi in pois:
    df['dist_' + poi['name']] = df.apply(
        lambda r: get_haversine_distance(
            r['latitude'], 
            r['longitude'], 
            poi['coord']), 
        axis=1)

Clustering de barrios

La característica neighbourhood tiene una cardinalidad muy alta que puede conducir a sobreajuste puesto que en algunos barrios hay pocos datos. Se propone, utilizando clusterización, una característica de cardinalidad intermedia entre barrios y distritos que agrupe barrios similares y que resulte más representativa para el estudio.

In [8]:
km = KModes(n_clusters=15, init='Huang', n_init=10, random_state=42)
df['nb_cluster'] = km.fit_predict(df[['price_med_occupation_per_accommodate', 'neighbourhood']])
clusters = df['nb_cluster'].copy()
df['nb_cluster'] = df['nb_cluster'].apply(lambda x: 'nb_' + str(x))
df.drop(['price_med_occupation_per_accommodate'], axis=1, inplace=True) # solo era para calcular clusters
In [9]:
cluster_map = pd.DataFrame(list(zip(df['neighbourhood'], clusters)), columns=['nb', 'cluster'])
cluster_map.drop_duplicates(inplace=True)

with open('src/geo/' + city + '.neighbourhoods.geojson') as f:
    city_nb = fix_geojson(json.load(f))
    
fig = go.Figure(go.Choroplethmapbox(
    geojson=city_nb,
    locations=cluster_map['nb'], 
    z=cluster_map['cluster'],                   
    colorscale=px.colors.qualitative.Vivid,                                
    marker_opacity=0.5, 
    marker_line_width=0.2
))

fig.update_layout(
    mapbox_style='carto-positron',
    mapbox_zoom=11, 
    mapbox_center={'lat':df['latitude'].mean(), 'lon':df['longitude'].mean()},
    margin={"r":0,"t":0,"l":0,"b":0},
    title='clusters',
    showlegend=False
)

fig.show()

Celdas S2

In [10]:
def get_s2(lat, lng):
    py_cellid = s2.CellId.from_lat_lng(
        s2.LatLng.from_degrees(lat, lng)
    )
    py_cellid = py_cellid.parent(12)
    return 's2_' + str(py_cellid.id())

df['s2'] = df.apply(lambda r: get_s2(r['latitude'], r['longitude']), axis=1)
In [11]:
df_s2 = df[['s2', 'latitude', 'longitude']]
s2_cells = sorted(df_s2['s2'].unique())
random.shuffle(s2_cells)
df_s2['idx'] = df_s2['s2'].apply(lambda x: s2_cells.index(x))
In [12]:
fig314 = go.Figure()

fig314.add_trace(go.Scattermapbox(
    lon=df_s2['longitude'],
    lat=df_s2['latitude'],
    mode='markers',
    marker_color=df_s2['idx'],
    text=df_s2['idx'],
    marker=dict(
        size=5,
        opacity=0.4,
        colorscale='spectral'
    )
))

fig314.update_layout(
    showlegend=False,
    mapbox_style='carto-positron',
    mapbox_zoom=11, 
    mapbox_center={'lat':df['latitude'].mean(), 'lon':df['longitude'].mean()},
    margin={"r":0,"t":0,"l":0,"b":0}
)

fig314.show()

Regiones Voronoi

In [13]:
poi_coords = list(map(lambda x: x['coord'], pois))
vor = spatial.Voronoi(poi_coords)

def get_voronoi_index(row):
    new_point = [row['latitude'], row['longitude']]
    point_index = np.argmin(np.sum((vor.points - new_point)**2, axis=1))
    return 'v_' + str(point_index)

df['voronoi'] = df.apply(lambda r: get_voronoi_index(r), axis=1)
spatial.voronoi_plot_2d(vor)
Out[13]:
In [14]:
df_voronoi = df[['voronoi', 'latitude', 'longitude']]
voronoi_cells = sorted(df_voronoi['voronoi'].unique())
df_voronoi['idx'] = df_voronoi['voronoi'].apply(lambda x: voronoi_cells.index(x))
In [15]:
fig315 = go.Figure()

fig315.add_trace(go.Scattermapbox(
    lon=df_voronoi['longitude'],
    lat=df_voronoi['latitude'],
    mode='markers',
    marker_color=df_voronoi['idx'],
    text=df_voronoi['idx'],
    marker=dict(
        size=5,
        opacity=0.4,
        colorscale='spectral'
    )
))

fig315.add_trace(
    go.Scattermapbox(
        lat=list(map(lambda x: x['coord'][0], pois)),
        lon=list(map(lambda x: x['coord'][1], pois)),
        text=list(map(lambda x: x['name'], pois)),
        mode='markers',
        marker=dict(
            size=8,
            opacity=0.9,
            color='black'
        )
    )
)

fig315.update_layout(
    showlegend=False,
    mapbox_style='carto-positron',
    mapbox_zoom=11, 
    mapbox_center={'lat':df['latitude'].mean(), 'lon':df['longitude'].mean()},
    margin={"r":0,"t":0,"l":0,"b":0}
)

fig315.show()

Conversión de características categóricas en dummies

In [16]:
print(df.shape)
dfd = pd.get_dummies(df)
print(dfd.shape)

target = 'price'
features = list(dfd.columns)
features.remove(target)
(5471, 65)
(5471, 215)

Partición en conjuntos de entrenamiento y test

In [17]:
x_train, x_test, y_train, y_test = train_test_split(
    dfd[features], 
    dfd[target],
    test_size=0.3,
    random_state=42
)

x_train = x_train.astype(float) # prevent conversion warnings

Modelo base: Random Forest

In [18]:
def eval_model(method, cols, df):
    model = RandomForestRegressor(random_state=42, n_estimators=200)    
    regressor = Pipeline([('model', model)])
    regressor.fit(x_train[cols], y_train)
    y_pred = regressor.predict(x_test[cols])
    r2 = r2_score(y_test, y_pred)
    mae = mean_absolute_error(y_test, y_pred)
    mse = mean_squared_error(y_test, y_pred)
    
    collect_results(cols, model, method, r2, mae, mse, skip_coef=True)
    importances = regressor.named_steps['model'].feature_importances_
    print_feature_importances(method, importances, df[cols])
    return y_pred

Estudio de la localización

In [19]:
neighbourhood_cols = [col for col in dfd if col.startswith('neighbourhood')]
dist_cols = [col for col in dfd if col.startswith('dist_')]
coord_cols = ['latitude', 'longitude']
nb_cluster_cols = [col for col in dfd if col.startswith('nb_cluster_')]
s2_cols = [col for col in dfd if col.startswith('s2_')]
voronoi_cols = [col for col in dfd if col.startswith('voronoi')]

Modelo sin variable geográfica

Este modelo registraría toda la variabilidad de precio que es debida a las propiedades de las viviendas sin considerar caractarísticas geográficas de ningún tipo.

In [20]:
cols = features.copy()
for c in [*neighbourhood_cols, *dist_cols, *coord_cols, *nb_cluster_cols, *s2_cols, *voronoi_cols]:
    if c in cols:
        cols.remove(c)
    
y_pred = eval_model('NO-GEO', cols, dfd)
NO-GEO
MAE 13.845
MSE 549.455
R2 0.639

Residuos

Se busca si existen zonas con un error positivo o negativo.

  • Lo que se puede asociar con puntos de interés: positivo
  • Zonas que los visitantes prefieren evitar: negativo
In [21]:
x_test['resid'] = y_test - y_pred
plt.hist(x_test['resid'], bins=50)
plt.show()

Residuos outliers

In [22]:
x_test2 = x_test.copy()
x_test2.reset_index(inplace=True)
outliers_idx = get_outliers_iqr(x_test2['resid'])[0]
remove_outliers(x_test2, outliers_idx, 'resid')
outliers between following bounds: -33.519075000000015 29.980124999999973
144 outliers to be removed with values: [-132.97049999999993, -120.24449999999993, -91.21500000000003, -88.13849999999994, -77.08499999999992, -74.60999999999993, -72.6884999999999, -64.60650000000001, -58.76099999999996, -57.71700000000001, -56.87100000000001, -55.675800000000024, -54.51750000000001, -53.22600000000001, -52.917749999999984, -52.573500000000045, -52.483499999999964, -52.39199999999988, -51.88499999999996, -49.788000000000025, -48.577500000000015, -47.992500000000014, -47.17799999999997, -46.791, -45.954000000000015, -44.69550000000007, -44.552249999999994, -43.217999999999975, -43.06050000000006, -42.50700000000006, -42.34949999999989, -39.90149999999993, -39.82499999999999, -39.721499999999935, -39.48000000000006, -39.024, -38.85075000000005, -38.173500000000004, -38.16900000000001, -37.711125, -37.32749999999993, -36.833175, -36.510750000000016, -36.436499999999924, -35.14050000000002, -34.92450000000002, -34.866, -34.56000000000002, -34.31250000000009, -34.30800000000004, -34.27199999999985, -33.77700000000003, 30.032999999999873, 30.43349999999998, 30.474000000000018, 30.568499999999958, 31.00500000000001, 32.29199999999999, 32.47649999999996, 33.07679999999999, 33.11999999999999, 34.65899999999999, 34.703999999999965, 35.99099999999997, 36.2025, 36.242999999999995, 36.27000000000001, 36.54674999999993, 36.67049999999996, 36.75150000000002, 37.02149999999996, 37.088999999999984, 37.14749999999997, 37.46699999999993, 38.11500000000004, 38.600999999999885, 38.76299999999999, 38.81070000000001, 38.83589999999995, 38.862000000000165, 40.26600000000002, 40.802249999999994, 41.15700000000001, 41.611499999999936, 43.16399999999997, 44.18099999999998, 44.90999999999998, 45.19799999999999, 45.401624999999974, 45.43199999999993, 45.45449999999998, 45.51299999999998, 46.07550000000009, 48.006, 48.34799999999997, 48.622499999999974, 50.96249999999999, 51.09299999999995, 52.838999999999956, 54.29699999999998, 54.32887499999999, 54.72449999999999, 56.54249999999996, 57.11400000000003, 57.672, 57.88350000000001, 60.0975, 61.042499999999976, 61.70400000000009, 62.585999999999984, 62.65080000000002, 63.58949999999996, 63.922499999999985, 65.84399999999997, 66.91949999999997, 68.37750000000001, 68.89499999999998, 69.89849999999998, 70.50599999999997, 71.75699999999996, 73.12949999999998, 73.30949999999999, 76.0455, 76.63499999999996, 77.77799999999999, 77.99646428571432, 78.12900000000002, 78.26587499999997, 79.0875, 82.53899999999999, 85.06349999999998, 86.04112500000001, 93.1881428571428, 104.63400000000004, 104.65199999999994, 107.03924999999998, 108.87300000000002, 111.95099999999996, 112.21424999999995, 112.7358, 113.12100000000002, 142.10924999999997, 232.9695, 326.844]
In [23]:
plt.hist(x_test2['resid'], bins=30)
plt.show()
In [24]:
fig1 = go.Figure(
    go.Scattermapbox(
        lon=x_test2['longitude'],
        lat=x_test2['latitude'],
        mode='markers',
        marker_color=x_test2['resid'],
        text=x_test2['resid'],
        marker=dict(
            opacity=0.8,
            colorscale=[
                [0.0, "rgb(165,0,38)"],
                [0.11, "rgb(215,48,39)"],
                [0.22, "rgb(244,109,67)"],
                [0.33, "rgb(253,174,97)"],
                [0.44, "rgb(254,224,144)"],
                [0.55, "rgb(224,243,248)"],
                [0.66, "rgb(171,217,233)"],
                [0.77, "rgb(116,173,209)"],
                [0.88, "rgb(69,117,180)"],
                [1.0, "rgb(49,54,149)"]
            ]
        )
    )
)

fig1.update_layout(
    mapbox_style='carto-positron',
    mapbox_zoom=11, 
    mapbox_center={'lat':x_test2['latitude'].mean(), 'lon':x_test2['longitude'].mean()},
    margin={"r":0,"t":0,"l":0,"b":0}
)

fig1.show()

Coordenadas

In [25]:
cols = features.copy()
for c in [*neighbourhood_cols, *dist_cols, *nb_cluster_cols, *s2_cols, *voronoi_cols]:
    if c in cols:
        cols.remove(c)
    
y_pred = eval_model('COORD', cols, dfd)
NO-GEO COORD
R2 0.639 0.632
MAE 13.845 13.820
MSE 549.455 560.419

Barrios

In [26]:
cols = features.copy()
for c in [*dist_cols, *coord_cols, *nb_cluster_cols, *s2_cols, *voronoi_cols]:
    if c in cols:
        cols.remove(c)
    
y_pred = eval_model('NB', cols, dfd)
NO-GEO COORD NB
R2 0.639 0.632 0.643
MAE 13.845 13.820 13.549
MSE 549.455 560.419 543.312

Cluster de barrios

In [27]:
cols = features.copy()
for c in [*neighbourhood_cols, *dist_cols, *coord_cols, *s2_cols, *voronoi_cols]:
    if c in cols:
        cols.remove(c)
    
y_pred = eval_model('CLUSTER-NB', cols, dfd)
NO-GEO COORD NB CLUSTER-NB
R2 0.639 0.632 0.643 0.647
MAE 13.845 13.820 13.549 13.578
MSE 549.455 560.419 543.312 537.725

Distancias a puntos de interés

In [28]:
cols = features.copy()
for c in [*neighbourhood_cols, *coord_cols, *nb_cluster_cols, *s2_cols, *voronoi_cols]:
    if c in cols:
        cols.remove(c)
    
y_pred = eval_model('DIST', cols, dfd)
NO-GEO COORD NB CLUSTER-NB DIST
R2 0.639 0.632 0.643 0.647 0.625
MAE 13.845 13.820 13.549 13.578 13.940
MSE 549.455 560.419 543.312 537.725 570.657

Voronoi

In [29]:
cols = features.copy()
for c in [*neighbourhood_cols, *nb_cluster_cols, *coord_cols, *dist_cols, *s2_cols]:
    if c in cols:
        cols.remove(c)
    
y_pred = eval_model('VORONOI', cols, dfd)
NO-GEO COORD NB CLUSTER-NB DIST VORONOI
R2 0.639 0.632 0.643 0.647 0.625 0.636
MAE 13.845 13.820 13.549 13.578 13.940 13.795
MSE 549.455 560.419 543.312 537.725 570.657 554.063

S2

In [30]:
cols = features.copy()
for c in [*neighbourhood_cols, *nb_cluster_cols, *coord_cols, *dist_cols, *voronoi_cols]:
    if c in cols:
        cols.remove(c)
    
y_pred = eval_model('S2', cols, dfd)
NO-GEO COORD NB CLUSTER-NB DIST VORONOI S2
R2 0.639 0.632 0.643 0.647 0.625 0.636 0.646
MAE 13.845 13.820 13.549 13.578 13.940 13.795 13.683
MSE 549.455 560.419 543.312 537.725 570.657 554.063 539.010

Automated feature engineering

In [31]:
auto_df = df.copy()
auto_df['auto_id'] = auto_df['price'].apply(lambda x: uuid.uuid1().int)
prices = auto_df['price']
auto_df.drop(['price'], axis=1, inplace=True, errors='ignore')
In [32]:
es = ft.EntitySet(id='airbnb')
es = es.entity_from_dataframe(
    entity_id='main',
    dataframe=auto_df,
    index='auto_id'
)
In [33]:
# available_transform_primitives = ft.primitives.list_primitives()
# print(available_transform_primitives[available_transform_primitives['type'] == 'transform'])

features_df, feature_names = ft.dfs(
    entityset=es,
    target_entity='main',
    trans_primitives=['subtract_numeric'],
    max_depth=2
)

# print(features_df.columns)
In [34]:
auto_df = features_df.copy()
auto_df.reset_index()
auto_df.drop(['auto_id'], axis=1, inplace=True, errors='ignore')

auto_df = pd.get_dummies(auto_df)
print(auto_df.shape)

auto_features = list(auto_df.columns)

x_train, x_test, y_train, y_test = train_test_split(
    auto_df, 
    prices,
    random_state=42
)

x_train = x_train.astype(float) # prevent conversion warnings
(5471, 1754)
In [35]:
y_pred = eval_model('AUTO-FT', auto_features, auto_df)
NO-GEO COORD NB CLUSTER-NB DIST VORONOI S2 AUTO-FT
R2 0.639 0.632 0.643 0.647 0.625 0.636 0.646 0.625
MAE 13.845 13.820 13.549 13.578 13.940 13.795 13.683 13.703
MSE 549.455 560.419 543.312 537.725 570.657 554.063 539.010 603.677